DEEP Project Unveils Next-Generation HPC Platform
At the final review, the 16 partners involved in the EU-funded project DEEP presented their innovative HPC platform: a prototype system with 500 TFlop/s peak performance. It implements the Cluster-Booster concept which has a lot in common with a turbocharged engine and operates with a full system software stack and programming environment engineered for performance and ease of use.
The DEEP system achieves the highest density and energy efficiency due to Eurotech's Aurora technology, while it showcases the EXTOLL HPC interconnect, and leverages Intel multi- and many-core processors. Porting and optimization of applications is facilitated by keeping strictly to standards (MPI and OpenMP), and by extending the task-based OmpSs model developed by Barcelona Supercomputing Center. ParaStation MPI, provided as part of ParTec's ParaStation ClusterSuite, has been turned into a Global MPI, the key system software component linking Cluster and Booster.
The DEEP prototype system is located at Jülich Supercomputing Centre (JSC) and is fully integrated with the hardware and software infrastructure on site. Initial application results clearly show the performance and efficiency potential of the system, and JSC plans to operate the machine for several years to come and make it available to external users. More information on the system can be found at http://www.fz-juelich.de/ias/jsc/deep.
(Contact: Dr. Estela Suarez, email@example.com)
JSC News, 2 December 2015